excalibur_refine_post_region

shallow

io.github.lonniev/excalibur-mcp · Verify this server

Refine a flagged region of a post with an LLM — server-side. The operator's LLM key stays in the vault and never leaves the server. Send the flagged ``region``, the surrounding ``full_text``, an optional ``instruction`` (what to change), and the editor's ``voice`` profile + ``bans`` (JSON array or comma list of banned constructions). Returns ``{"success": true, "suggestions": [...3 strings...]}``. Paid: the AI cost is metered as a tollbooth fare. The fare is refunded if no LLM key is configured or the upstream call returns nothing.

100.0/100

1 trials · measured 8 days ago

excalibur_refine_post_region scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against io.github.lonniev/excalibur-mcp, measured 25 Aug 2026 under methodology v0.2.0. Every measured component scored 100.

Component breakdown

ComponentWeightValue
Reliability35%not applicable
Schema integrity25%100.0
Failure behaviour15%not applicable
Latency15%not applicable
Concurrency10%not applicable

Tool details

Transport
remote
Credential class
self-provisionable
Category
Content & media
Input schema
not declared
Output schema
not declared
Side-effect classification
unclassified

Score history

DayScoreTierMethodology
2026-08-25100.0shallowv0.2.0

Probe evidence

ProbeOutcomes
schema_integritypass: 1

Raw request/response logs are not archived yet — the outcome counts above are drawn directly from every recorded trial.

Embed this score

Available for every tool, scored or not — not a verification perk. Always links back to this page.

Vouch score: excalibur_refine_post_region
[![Vouch score](https://vouch.tools/api/tools/1a1d2917-0116-4161-81e6-df6b1b472dcc/badge.svg)](https://vouch.tools/tools/1a1d2917-0116-4161-81e6-df6b1b472dcc)
excalibur_refine_post_region — Vouch